Comments (2)
Hi,
You're right, you can compensate the lost boundary pixels using zero-padding, instead of mirroring. In that case the network will have to deal with the discontinuity in the input (at the boundary), which may or may not work as well as mirroring. We have not tested this.
If you will test this, let us know the results.
from cascaded-fcn.
Thanks for your answer!
As I realized only later, the zero padding of the filters would also effectively introduce zeros to the borders of the feature maps, so it would seem like it might cause problems throughout the network. But surprisingly enough there seems to be no penalty in the quality of results on the datasets that I tried it on so far.
There are two different MR datasets that I tried it on in a three-fold cross-validation each. In the first dataset, the filter-padding made it possible to use an input size of 256x256 instead of 572x572. The training then only took 30% of the time and used only 37% as much memory on the GPU. The result was curiously slightly better than when using the enlarged image, but it might just be a random variation.
On the second dataset the size was reduced from 320x320 to 128x128 and the training then took about 45% of the previous time and 55% of the GPU memory. The results were slightly better or worse than before, depending on the epoch, and the difference was very small.
Maybe the feature maps are so sparse that the zero padding does not make a big difference, or alternatively the later layers adapt to the effects caused by the padded filters. In any case it seems worth it for faster experiments, although in the end I might try the best setup on the enlarged data without padded filters again just to be sure.
from cascaded-fcn.
Related Issues (20)
- The dropbox link of weights.caffemodel were expired HOT 6
- Model Address invalidation? HOT 2
- Why is my prediction so bad?
- Batch normalization not used? Step2 dataset? HOT 3
- question HOT 3
- #question. Do we need to train for step 2 in cascaded FCN? HOT 1
- #Question:The results in the Docker are inconsistent with the illustrations in the paper
- Class Weight Selection HOT 1
- Pretrained TensorFlow Models HOT 5
- Result is very worse followed by the ipynb file HOT 3
- A question about training sets and metrics
- Question:The results for the code are error HOT 11
- Need help in preprocessing HOT 1
- Example Docker does not work (crashes) HOT 6
- Issue with prediction method
- Weights for MRI model
- TypeError: slice indices must be integers or None or have an __index__ method`
- How testing and training is done
- training data format HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cascaded-fcn.